saudade

human in the loop @poolsideai

[saudade @eloquake]

Laguna XS.2 is free to train on Prime Intellect Lab this month.
you know what to do

[Prime Intellect @PrimeIntellect]

This month, Poolside’s Laguna XS.2 is free to train on Prime Intellect Lab. First come, first serve while reserved capacity lasts.

[Poolside @poolsideai]

Laguna M.1 is #1 on @kilocode today.
Good to see Laguna getting put to work.

[saudade @eloquake]

Over the moon about our first ever research hack at Poolside 💙
Shout to all the participants, partners, and ofc @poolsideai team who made it possible!

[Poolside @poolsideai]

What a weekend. Around 30 teams showed up to build on Laguna XS.2, and the bar was very, very high.

Winners below 🏆

1st: Overthinking Machines Labs
@emilfristed
Pseudo-full-duplex with text-only models through dialogue modeling with silence tokens.
https://t.co/rP4BZWrtrz

2nd: Coding Kernels by the Pool
Charlie Masters, Evan O’Leary, Jessica Mak
Laguna-Dense: a ~3B fully dense distillation of Laguna XS.2 for generating CUDA kernels from PyTorch.
https://t.co/OLmGezfGqF

3rd: attnvq
@alaradirik
Attention-aware product vector quantization of KV caches.
https://t.co/SwXmcIEOhn

Honorary mention: Laguna Vision
Aaron Kazah @aaronkazah
A SigLIP vision encoder + resampler + LoRA adapters, trained on 300k examples to give Laguna XS.2 a native visual input path.
https://t.co/dgrtgI7eoj

Huge congrats to the winners, and thank you to everyone who hacked, demoed, judged, helped, and pushed Laguna XS.2 in directions we would not have found on our own!

@nvidia @PrimeIntellect @adaption_ai @huggingface

[saudade @eloquake]

Poolside office in London
@iamgrigorev is cooking

[Poolside @poolsideai]

Today we’re publishing the technical report behind Laguna M.1 and Laguna XS.2.

This report opens up more of what went into them: Model Factory, pre-training data, distributed training, post-training, agent RL, quantization, and evaluation.

https://t.co/RWk2F9IrAI

[saudade @eloquake]

even Greg gets it
coding agents belong poolside
curl -fsSL https://t.co/COaYFoM5lf | sh

[Greg Brockman @gdb]

good location to build

[Louis Knight-Webb @tokengobbler]

Super pumped for the @poolsideai research hackathon on the 29th. Will be a great crowd, but ngl worth going just for a shot at winning the DGX Spark...

[saudade @eloquake]

ok but you could simply

come to London next Friday
play with Laguna XS.2 weights
build smth cool
win the interesting little guy
go home and keep tinkering

seems like a good weekend to me

https://t.co/IdXZWvJY9k

[0xSero @0xSero]

Such an interesting little guy

[saudade @eloquake]

run your own research lab over a weekend!

[Poolside @poolsideai]

setup hell kills good RL ideas.

so we’re giving researchers Laguna XS.2, @PrimeIntellect Lab, and a weekend in London to run the whole loop:

tasks → evals → rewards → training → rollouts → adapters → inference

14 days to go.

come touch the weights:
https://t.co/0HnfF6TuQf

[saudade @eloquake]

Just move to London.

[Financial Times @FT]

King’s Cross is the Silicon Roundabout of AI https://t.co/Sb4rBcvb7x | opinion

[saudade @eloquake]

@AlexJonesax Come join us at the hackathon!!

[will brown @willccbb]

“train a custom 30B MoE agent model with reinforcement learning in a real harness” is now easy and cost-effective enough that it can be a hackathon format

[saudade @eloquake]

tbh I have never had a job that gets only more and more exciting every week 💙

@poolsideai is a rocket ship 🚀

[saudade @eloquake]

@caffeinum Tell your London friends to come!

[saudade @eloquake]

Londonmaxxing is so back.

Cracked researchers, come build with usss 👾

[Poolside @poolsideai]

Poolside is hosting a 2-day model research hackathon in London.

Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intellect Lab.

Dates: May 29–30
Partners: @nvidia + @PrimeIntellect + @huggingface
Prize: NVIDIA DGX Spark

Agents need better models.
Better models need cracked researchers.

Link below.

[saudade @eloquake]

found it very useful as a soft non-technical extrovert

[Yacine Mahdid @yacinelearning]

https://t.co/W3nv57VYiB

[saudade @eloquake]

if gossip girl was a job title
it’s now on my resume

[saudade @eloquake]

going all in or hedging risks?

[saudade @eloquake]

officially obsessed

[Silicon Mania @siliconmania]

you asked for it. so we made it.

say hi to https://t.co/qxa4fZgVgG

each reference of the weekly tech recaps. explained.

its finally time to understand all of them. enjoy.

[saudade @eloquake]

@iamgrigorev lfg!!!